Use of artificial neural networks for prediction of discharge coefficient of triangular labyrinth side weir in curved channels

Side weirs have been extensively used in hydraulic and environmental engineering applications. The discharge coefficient of the triangular labyrinth side weirs is 1.5-4.5 times higher than that of rectangular side weirs. This study aims to estimate the discharge coefficient (C_d) of triangular labyrinth side weir in curved channel by using artificial neural networks (ANN). In this study, 7963 laboratory test results are used for determining the C_d. The performance of the ANN model is compared with multiple nonlinear and linear regression models. Root mean square errors (RMSE), mean absolute errors (MAE) and correlation coefficient (R) statistics are used as comparing criteria for the evaluation of the models’ performances. Based on the comparisons, it was found that the neural computing technique could be employed successfully in modeling discharge coefficient from the available experimental data. There were good agreements between the measured values and the values obtained using the ANN model. It was found that the ANN model with RMSE of 0.1658 in validation stage is superior in estimation of discharge coefficient than the multiple nonlinear and linear regression models with RMSE of 0.2054 and 0.2926, respectively.     

Predicting discharge capacity of triangular labyrinth side weir located on a straight channel by using an adaptive neuro-fuzzy technique

Side weirs are widely used for flow diversion in irrigation, land drainage, urban sewage systems and also in intake structures. It is essential to correctly predict the discharge coefficient for hydraulic engineers involved in the technical and economical design of side weirs. In this study, the discharge capacity of triangular labyrinth side weirs is estimated by using adaptive neuro-fuzzy inference system (ANFIS). Two thousand five hundred laboratory test results are used for determining discharge coefficient of triangular labyrinth side weirs. The performance of the ANFIS model is compared with multi nonlinear regression models. Root mean square errors (RMSE), mean absolute errors (MAE) and correlation coefficient (R) statistics are used as comparing criteria for the evaluation of the models’ performances. Based on the comparisons, it was found that the ANFIS technique could be employed successfully in modeling discharge coefficient from the available experimental data. There are good agreements between the measured values and the values obtained using the ANFIS model. It is found that the ANFIS model with RMSE of 0.0699 in validation stage is superior in estimation of discharge coefficient than the multiple nonlinear and linear regression models with RMSE of 0.1019 and 0.1507, respectively.     

Neural networks for estimation of discharge capacity of triangular labyrinth side-weir located on a straight channel

Side-weirs are flow diversion devices widely used in irrigation, land drainage, and urban sewage systems. It is essential to correctly predict the discharge coefficient for hydraulic engineers involved in the technical and economical design of side-weirs. In this study, the discharge capacity of triangular labyrinth side-weirs is estimated by using artificial neural networks (ANN). Two thousand five hundred laboratory test results are used for determining discharge coefficient of triangular labyrinth side-weirs. The performance of the ANN model is compared with multi nonlinear regression models. Root mean square errors (RMSE), mean absolute errors (MAE) and correlation coefficient (R) statistics are used as comparing criteria for the evaluation of the models’ performances. Based on the comparisons, it was found that the neural computing technique could be employed successfully in modelling discharge coefficient from the available experimental data. There were good agreements between the measured values and the values obtained using the ANN model. It was found that the ANN model with RMSE of 0.0674 in validation stage is superior in estimation of discharge coefficient than the multiple nonlinear and linear regression models with RMSE of 0.1019 and 0.1507, respectively.     

A variational mode decompoisition approach for analysis and forecasting of economic and financial time series

The empirical mode decomposition (EMD) has been successfully applied to adaptively decompose economic and financial time series for forecasting purpose. Recently, the variational mode decomposition (VMD) has been proposed as an alternative to EMD to easily separate tones of similar frequencies in data where the EMD fails. The purpose of this study is to present a new time series forecasting model which integrates VMD and general regression neural network (GRNN). The performance of the proposed model is evaluated by comparing the forecasting results of VMD-GRNN with three competing prediction models; namely the EMD-GRNN model, feedforward neural networks (FFNN), and autoregressive moving average (ARMA) process on West Texas Intermediate (WTI), Canadian/US exchange rate (CANUS), US industrial production (IP) and the Chicago Board Options Exchange NASDAQ 100 Volatility Index (VIX) time series are used for experimentations. Based on mean absolute error (MAE), mean absolute percentage error (MAPE), and the root mean of squared errors (RMSE), the analysis results from forecasting demonstrate the superiority of the VMD-based method over the three competing prediction approaches. The practical analysis results suggest that VMD is an effective and promising technique for analysis and prediction of economic and financial time series.     

Option valuation based on the neural regression model

In this article, a neural regression (NR) model, which produces nonlinear coefficients of multiple regression model based on neural networks, is introduced to capture the option valuation’s nonlinear characteristics effectively. The traditional linear regression uses the least-squares estimator to estimate the coefficient of a linear regression and thus may only produce suboptimal solutions. However, Applying neural networks to forecast volatility in option pricing has increased in popularity in recent years since many studies have indicated that the conventional option pricing models are not accurate enough. Our proposed neural regression model devotes to evaluate option values to improve on the tracking error in the measurement of hedging capability. The NR model uses the variables introduced by the Black–Scholes Model and applies the multiple regressions (MR) model to re-price option values. It is worth noting that each corresponding weight coefficient in MR is constructed by a complete neural network rather than by a scalar value. By capturing the nonlinear behaviors of option pricing, our proposed NR model has lower tracking error and better hedging capability than the BS model and other studies.     

Assessing neural networks with wavelet denoising and regression models in predicting diel dynamics of eddy covariance-measured latent and sensible heat fluxes and evapotranspiration

Eddy covariance (EC)-measured data were used to develop multiple nonlinear regression (MNLR) models of latent (LE) and sensible heat (H _s) fluxes, and micrometeorological station-measured actual evapotranspiration (ET). Discrete wavelet transform (DWT) with symmlets (sym10), coiflets (coif10), and daubechies (db10) was used to decompose time series signals of LE, H _s, and ET into frequency components in order to feed denoised output data into 26 artificial neural networks (ANNs) with different learning algorithms, based on independent validation-derived values of coefficient of determination (r ²), root mean square error (RMSE), mean absolute error (MAE), wavelet neural networks (WNNs) with coif10-1 and db10-1 outperformed ANNs, and MNLR models. The best ones out of 26 WNNs appeared to be multilayer perceptrons (MLPs) for LE and H _s, and time-delay network (TDNN) for ET, while the best ones out of 26 ANNs were determined as TDNN for LE, MLP for H _s, and generalized feedforward network (GFF) for ET. The combination of batch mode and Levenberg–Marquardt algorithm was adopted in the ANNs and WNNs more frequently and generated better accuracy metrics than the combinations of online mode and Momentum algorithm, and batch mode and Momentum algorithm.     

Forecasting highway casualties under the effect of railway development policy in Turkey using artificial neural networks

This study presents forecast of highway casualties in Turkey using nonlinear multiple regression (NLMR) and artificial neural network (ANN) approaches. Also, the effect of railway development on highway safety using ANN models was evaluated. Two separate NLMR and ANN models for forecasting the number of accidents (A) and injuries (I) were developed using 27 years of historical data (1980–2006). The first 23 years data were used for training, while the remaining data were utilized for testing. The model parameters include gross national product per capita (GNP-C), numbers of vehicles per thousand people (V-TP), and percentage of highways, railways, and airways usages (TSUP-H, TSUP-R, and TSUP-A, respectively). In the ANN models development, the sigmoid and linear activation functions were employed with feed-forward back propagation algorithm. The performances of the developed NLMR and ANN models were evaluated by means of error measurements including mean absolute percentage error (MAPE), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R ²). ANN models were used for future estimates because NLMR models produced unreasonably decreasing projections. The number of road accidents and as well as injuries was forecasted until 2020 via different possible scenarios based on (1) taking TSUPs at their current trends with no change in the national transport policy at present, and (2) shifting passenger traffic from highway to railway at given percentages but leaving airway traffic with its current trend. The model results indicate that shifting passenger traffic from the highway system to railway system resulted in a significant decrease on highway casualties in Turkey.     

Flood flow forecasting using ANN,ANFIS and regression models

Flood prediction is an important for the design, planning and management of water resources systems. This study presents the use of artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), multiple linear regression (MLR) and multiple nonlinear regression (MNLR) for forecasting maximum daily flow at the outlet of the Khosrow Shirin watershed, located in the Fars Province of Iran. Precipitation data from four meteorological stations were used to develop a multilayer perceptron topology model. Input vectors for simulations included the original precipitation data, an area-weighted average precipitation and antecedent flows with one- and two-day time lags. Performances of the models were evaluated with the RMSE and the R ². The results showed that the area-weighted precipitation as an input to ANNs and MNLR and the spatially distributed precipitation input to ANFIS and MLR lead to more accurate predictions (e.g., in ANNs up to 2.0 m³ s^?1 reduction in RMSE). Overall, the MNLR was shown to be superior (R ² = 0.81 and RMSE = 0.145 m³ s^?1) to ANNs, ANFIS and MLR for prediction of maximum daily flow. Furthermore, models including antecedent flow with one- and two-day time lags significantly improve flow prediction. We conclude that nonlinear regression can be applied as a simple method for predicting the maximum daily flow.     

Artificial neural network approaches for prediction of backwater through arched bridge constrictions

This paper presents the findings of laboratory model testing of arched bridge constrictions in a rectangular open channel flume whose bed slope was fixed at zero. Four different types of arched bridge models, namely single opening semi-circular arch (SOSC), multiple opening semi-circular arch (MOSC), single opening elliptic arch (SOE), and multiple opening elliptic arch (MOE), were used in the testing program. The normal crossing (ϕ = 0), and five different skew angles (ϕ = 10°, 20°, 30°, 40°, and 50°) were tested for each type of arched bridge model. The main aim of this study is to develop a suitable model for estimating backwater through arched bridge constrictions with normal and skewed crossings. Therefore, different artificial neural network approaches, namely multi-layer perceptron (MLP), radial basis neural network (RBNN), generalized regression neural network (GRNN), and multi-linear and multi-nonlinear regression models, MLR and MNLR, respectively were used. Results of these experimental studies were compared with those obtained by the MLP, RBNN, GRNN, MLR, and MNLR approaches. The MLP produced more accurate predictions than those of the others.     

Two-stage intonation modeling using feedforward neural networks for syllable based text-to-speech synthesis

This paper proposes a two-stage feedforward neural network (FFNN) based approach for modeling fundamental frequency (F₀) values of a sequence of syllables. In this study, (i) linguistic constraints represented by positional, contextual and phonological features, (ii) production constraints represented by articulatory features and (iii) linguistic relevance tilt parameters are proposed for predicting intonation patterns. In the first stage, tilt parameters are predicted using linguistic and production constraints. In the second stage, F₀ values of the syllables are predicted using the tilt parameters predicted from the first stage, and basic linguistic and production constraints. The prediction performance of the neural network models is evaluated using objective measures such as average prediction error (μ), standard deviation (σ) and linear correlation coefficient (γ_X,Y). The prediction accuracy of the proposed two-stage FFNN model is compared with other statistical models such as Classification and Regression Tree (CART) and Linear Regression (LR) models. The prediction accuracy of the intonation models is also analyzed by conducting listening tests to evaluate the quality of synthesized speech obtained after incorporation of intonation models into the baseline system. From the evaluation, it is observed that prediction accuracy is better for two-stage FFNN models, compared to the other models.     

Estimation of pressuremeter modulus and limit pressure of clayey soils by various artificial neural network models

The main purpose of the present study is to develop some artificial neural network (ANN) models for the prediction of limit pressure (P _L) and pressuremeter modulus (E _M) for clayey soils. Moisture content, plasticity index, and SPT values are used as inputs in the ANN models. To get plausible results, the number of hidden layer neurons in all models is varied between 1 and 5. In addition, both linear and nonlinear activation functions are considered for the neurons in output layers while a nonlinear activation function is employed for the neurons in the hidden layers of all models. Logistic activation function is used as a nonlinear activation function. During the modeling studies, total eight different ANN models are constructed. The ANN models having two outputs produced the worst results, independent from activation function. However, for P _L, the best results are obtained from the feed-forward neural network with five neurons in the hidden layer, and logistic activation function is employed in the output neuron. For E _M, the best model producing the most acceptable results is Elman recurrent network model, which has 4 neurons in the neurons in the hidden layer, and linear activation function is used for the output neuron. Finally, the results show that the ANN models produce the more accurate results than the regression-based models. In the literature, when empirical equations based on regression analysis were used, the best root mean square error (RMSE) values obtained to date for P _L and E _M have been 0.43 and 5.65, respectively. In this study, RMSE values for P _L and E _M were found to be 0.20 and 2.99, respectively, by using ANN models. It was observed that using ANN approach drastically increases the prediction accuracy in terms of RMSE criterion.     

Comparative study of metamodelling techniques in building energy simulation: Guidelines for practitioners

Computer simulation of real system behaviour is increasingly used in research and development. As simulation models become more reliable, they also often become more complex to capture the progressive complexity of the real system. Calculation time can be a limiting factor for using simulation models in optimisation studies, for example, which generally require multiple simulations. Instead of using these time-consuming simulation models, the use of metamodels can be considered. A metamodel approximates the original simulation model with high confidence via a simplified mathematical model. A series of simulations then only takes a fraction of the original simulation time, hence allowing significant computational savings.In this paper, a strategy that is both reliable and time-efficient is provided in order to guide users in their metamodelling problems. Furthermore, polynomial regression (PR), multivariate adaptive regression splines (MARS), kriging (KR), radial basis function networks (RBF), and neural networks (NN) are compared on a building energy simulation problem. We find that for the outputs of this example and based on Root Mean Squared Error (RMSE), coefficient of determination (R²), and Maximal Absolute Error (MAE), KR and NN are the overall best techniques. Although MARS perform slightly worse than KR and NN, it is preferred because of its simplicity. For different applications, other techniques might be optimal.     

Damage detection in Timoshenko beam structures by multilayer perceptron and radial basis function networks

This study investigates the efficiency of artificial neural networks (ANNs) in health monitoring of pristine and damaged beam-like structures. Beam modeling is based on Timoshenko theory. Two commonly used network models, multilayer perceptron (MLP) and radial basis neural network (RBNN), are used. Beam material and geometrical properties, beam end conditions and dynamically obtained data are used as input to the neural networks. The combinations of these parameters yield umpteenth input data. Therefore, to examine the effectiveness of ANNs, the frequency of intact beams is first tried to be determined by the network models, given the material and geometrical characteristics of beam elements and support conditions. The methodology to compute the vibrational data utilized in training the networks is provided. Showing the robustness of network models, the second stage of the study is carried out. At this stage, the crack parameters (e.g. the location and severity of crack) are estimated by the ANNs using the beam properties, beam end conditions and vibrational data, which consist of natural frequencies and mode shape rotation values. Despite the multiplexed input data, no data reduction schemes or multistage computations are executed in training and validation of neural network models. As a result of analysis runs, the optimal MLP and RBNN models are determined. Comparison of these models shows that the optimal RBNN algorithm performs better. The effectiveness of optimal ANN models in the presence of noise is also presented. As a conclusion, the trained network can be used as a diagnosis method in structural health monitoring of beam-like structures.     

非线性混合像元分解的可视化分析与评价

混合像元的非线性分解通常采用神经元网络模型来拟合,普遍缺乏线性分解模型简单明确的物理意义,导致难于了解像元混合的特点及误差分布的模式。为此,提出均方根误差、双变量统计、置信度估计和混合复杂度等可视化方法来评价非线性混合模型分解的结果,直观地表达出影像中像元的分解精度、混合程度以及误差分布模式等,从而理解非线性混合模型分解的某些特点。实验以投影追踪学习网络（PPLN）为例,利用MODIS与ETM+数据,对MODIS混合像元分解进行了可视化分析,一定程度上展现了PPLN分解的某些特点。通过与反向传播神经网络(BPNN)分解比较结果表明,PPLN具有较高的分解精度,总体误差从0.182 8降低到0.171 7,降低了大约6.5%,且可视化分析表明混合程度较大的区域发生在城区和稀疏植被覆盖区。     

Artificial Neural Network Approach to Data Matrix Laser Direct Part Marking

Certain applications have recently appeared in industry where a traditional bar code printed on a label will not survive because the item to be tracked has to be exposed to harsh environments. Laser direct-part marking is a manufacturing process used to create permanent marks on a substrate that could help to alleviate this problem. In this research, artificial neural networks were employed to model the laser direct-part marking process of Data Matrix symbols on carbon steel substrates. Several experiments were conducted to study the laser direct-part marking process and to generate data to serve as training, validation and testing data sets in the artificial neural networks modeling process. Two performance measures, mean squared error and correlation coefficient, were utilized to assess the performance of the artificial neural network models. Single-output artificial neural network models corresponding to four performance measures specific to the Data Matrix bar code symbology were found to have good learning and predicting capabilities. The single-output artificial neural network models were compared to equivalent multiple linear regression models for validation purposes. The prediction capability of the single-output artificial neural network models with respect to laser direct-part marking of Data Matrix symbols on carbon steel substrates was superior to that of the multiple linear regression models.     

Predicting discharge coefficient of triangular labyrinth weir using extreme learning machine,artificial neural network and genetic programming

Weirs are a type of hydraulic structure used to direct and transfer water flows in the canals and overflows in the dams. The important index in computing flow discharge over the weir is discharge coefficient (C _d). The aim of this study is accurate determination of the C _d in triangular labyrinth side weirs by applying three intelligence models [i.e., artificial neural network (ANN), genetic programming (GP) and extreme learning machine (ELM)]. The calculated discharge coefficients were then compared with some experimental results. In order to examine the accuracy of C _d predictions by ANN, GP and ELM methods, five statistical indices including coefficient of determination (R ²), root-mean-square error (RMSE), mean absolute percentage error (MAPE), SI and δ have been used. Results showed that R ² values in the ELM, ANN and GP methods were 0.993, 0.886 and 0.884, respectively, at training stage and 0.971, 0.965 and 0.963, respectively, at test stage. The ELM method, having MAPE, RMSE, SI and δ values of 0.81, 0.0059, 0.0082 and 0.81, respectively, at the training stage and 0.89, 0.0063, 0.0089 and 0.88, respectively, at the test stage, was superior to ANN and GP methods. The ANN model ranked next to the ELM model.

     

Estimation of high-spatial resolution clear-sky longwave downward and net radiation over land surfaces from MODIS data

Surface downwelling longwave radiation (LWDN) and surface net longwave radiation (LWNT) are two components in the surface radiation budget. In this study, we developed new linear and nonlinear models using a hybrid method to derive instantaneous clear-sky LWDN over land from the Moderate Resolution Imaging Spectroradiometer (MODIS) TOA radiance at 1 km spatial resolution. The hybrid method is based on extensive radiative transfer simulation (physical) and statistical analysis (statistical). Linear and nonlinear models were derived at 5 sensor view zenith angles (0°, 15°, 30°, 45°, and 60°) to estimated LWDN using channels 27-29 and 31-34. Separate models were developed for daytime and nighttime observations. Surface pressure effect was considered by incorporating elevation in the models. The linear LWDN models account for more than 92% of variations of the simulated data sets, with standard errors less than 16.27 W/m² for all sensor view zenith angles. The nonlinear LWDN models explain more than 93% of variations, with standard errors less than 15.20 W/m². The linear and nonlinear LWDN models were applied to both Terra and Aqua TOA radiance and validated using ground data from six SURFRAD sites. The nonlinear models outperform the linear models at five sites. The averaged root mean squared errors (RMSE) of the nonlinear models are 17.60 W/m² (Terra) and 16.17 W/m² (Aqua), with averaged RMSE ~ 2.5 W/m² smaller than that of the linear models. LWNT was estimated using the nonlinear LWDN models and the artificial neural network (ANN) model method that predicts surface upwelling longwave radiation. LWNT was also validated using the same six SURFRAD sites. The averaged RMSEs are 17.72 (Terra) and 16.88 (Aqua) W/m²; the averaged biases are − 2.08 (Terra) and 1.99 (Aqua) W/m². The LWNT RMSEs are less than 20 W/m² for both Terra and Aqua observations at all sites.     

Analysis and Modeling of Naturalness in Handwritten Characters

In this paper, we define the naturalness of handwritten characters as being the difference between the strokes of the handwritten characters and the archetypal fonts on which they are based. With this definition, we mathematically analyze the relationship between the font and its naturalness using canonical correlation analysis (CCA), multiple linear regression analysis, feedforward neural networks (FFNNs) with sliding windows, and recurrent neural networks (RNNs). This analysis reveals that certain properties of font character strokes do not have a linear relationship with their naturalness. In turn, this suggests that nonlinear techniques should be used to model the naturalness, and in our investigations, we find that an RNN with a recurrent output layer performs the best among four linear and nonlinear models. These results indicate that it is possible to model naturalness, defined in our study as the difference between handwritten and archetypal font characters but more generally as the difference between the behavior of a natural system and a corresponding basic system, and that naturalness learning is a promising approach for generating handwritten characters.     

Prediction of soil adsorption coefficient based on deep recursive neural network

It is expensive and time consuming to measure soil adsorption coefficient (logKoc) of compounds using traditional methods, and some existing models show lower accuracies. To solve these problems, a deep learning (DL) method based on undirected graph recursive neural network (UG-RNN) is proposed in this paper. Firstly, the structures of molecules are represented by directed acyclic graphs (DAG) using RNN model; after that when a number of such neural networks are bundled together, they form a multi-level and weight sharing deep neural network to extract the features of molecules; Third, logKoc values of compounds have been predicted using back-propagation neural network. The experimental results show that the UG-RNN model achieves a better prediction effect than some shallow models. After five-fold cross validation, the root mean square error (RMSE) value is 0.46, the average absolute error (AAE) value is 0.35, and the square correlation coefficient (R²) value is 0.86.     

RBFNN versus FFNN for daily river flow forecasting at Johor River,Malaysia

Streamflow forecasting can have a significant economic impact, as this can help in water resources management and in providing protection from water scarcities and possible flood damage. Artificial neural network (ANN) had been successfully used as a tool to model various nonlinear relations, and the method is appropriate for modeling the complex nature of hydrological systems. They are relatively fast and flexible and are able to extract the relation between the inputs and outputs of a process without knowledge of the underlying physics. In this study, two types of ANN, namely feed-forward back-propagation neural network (FFNN) and radial basis function neural network (RBFNN), have been examined. Those models were developed for daily streamflow forecasting at Johor River, Malaysia, for the period (1999–2008). Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static neural networks. The results demonstrate that RBFNN model is superior to the FFNN forecasting model, and RBFNN can be successfully applied and provides high accuracy and reliability for daily streamflow forecasting.